Support vector regression has been proposed in a number of image processing tasks including blind image deconvolution, image denoising and single frame super-resolution. As for other machine learning methods, the training is slow. In this paper, we attempt to address this issue by reducing the feature dimensionality through Principal Component Analysis (PCA). Our single frame supper-resolution ...

We propose a general model for joint inference in correlated natural language processing tasks when fully annotated training data is not available, and apply this model to the dual tasks of word sense disambiguation and verb subcategorization frame determination. The model uses the EM algorithm to simultaneously complete partially annotated training sets and learn a generative probabilistic mod...

Convolutional networks reach top quality in pixel-level object tracking but require a large amount of training data (1k∼10k) to deliver such results. We propose a new training strategy which achieves state-of-the-art results across three evaluation datasets while using 20×∼100× less annotated data than competing methods. Instead of using large training sets hoping to generalize across domains, ...

The presence of a corresponding talking face has been shown to significantly improve speech intelligibility in noisy conditions and for hearing impaired population. In this paper, we present a system that can generate landmark points of a talking face from an acoustic speech in real time. The system uses a long short-term memory (LSTM) network and is trained on frontal videos of 27 different sp...

in this paper we get some results and applications for duals and approximate duals of g-frames in hilbert spaces. in particular, we consider the stability of duals and approximate duals under bounded operators and we study duals and approximate duals of g-frames in the direct sum of hilbert spaces. we also obtain some results for perturbations of approximate duals.

in this paper, g-dual function-valued frames in l2(0;1) are in-troduced. we can achieve more reconstruction formulas to ob-tain signals in l2(0;1) by applying g-dual function-valued framesin l2(0;1).